Why Most AI Models Fail ❌ — Evaluate & Deploy AI Agents on Databricks

Description

Learn how to build, evaluate, and deploy a production-ready RAG (Retrieval-Augmented Generation) AI agent in Databricks using LangChain, MLflow, Vector Search, and Llama 3. The code can be found here: https://github.com/apostolos1927/RAG Follow me on social media: LinkedIn: [www.linkedin.com/in/apostolos-athanasiou-9a0baa119](http://www.linkedin.com/in/apostolos-athanasiou-9a0baa119) GitHub: https://github.com/apostolos1927/ Instagram: https://www.instagram.com/thedataengineeringchannel X(Twitter): https://x.com/DataEngineerC The documentation can be found here: -https://docs.databricks.com/aws/en/generative-ai/agent-framework/log-agent#specify-resources-for-pyfunc-or-langchain-agent -https://docs.databricks.com/aws/en/mlflow3/genai/eval-monitor/concepts/judges/ -https://docs.databricks.com/aws/en/generative-ai/agent-evaluation/evaluation-set#sample-evaluations-sets In this hands-on tutorial, we create a complete ecommerce AI assistant that: Uses Databricks Vector Search Retrieves product data using RAG Uses LangChain agents and tools Evaluates responses with MLflow GenAI evaluation Detects hallucinations and groundedness Deploys the model to a Databricks serving endpoint Tech Stack: Databricks, MLflow, LangChain, Llama 3, Vector Search, Python, GenAI, RAG Timestamps: 00:00 – Intro 01:10 – Model Evaluation and Deployment in Databricks